Vehicle motion-state-estimation using distributed sensing

Knowing the position and speed of the vehicles on the road network in real-time is one of the major challenges that vehicle control and traffic management applications are facing. Wireless sensor networks received significant attention in the last decade and successful research put them in the forefront to answer this challenge. Wireless sensor networks are a new class of observation systems with a large amount of nodes communicating with each other via a wireless network channel. In this paper such a system is used to firstly detect a vehicle and secondly estimate its motion-state. The nodes are evenly distributed in a along the road surface and each node can detect when a vehicle passes. With the known position of the individual nodes, a motion-state of the vehicle is estimated. Three state-estimators are analyzed in this paper; a synchronous Kalman filter, an asynchronous Kalman filter and a mixture of Gaussians. After designing these state-estimators, simulations are performed to assess their performance.